NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PMKMAG7HH37W1RJXJC7GX
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.5s
Cost:
$0.010230
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
99.83%
Dialogue to Total Word Ratio
(details)
60.0089%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly crouched behind the privet hedge, studying the backyard like a general facing a bouncy castle. Balloons bobbed from the fence, a clown twisted balloons into suspiciously weak swords, and a table sagged beneath a mountain of glittering presents. “Bill,” she whispered, “count the guards.” Bill adjusted his fake mustache. “Seven children, one clown, two mothers, and a dog wearing a tiara.” “The dog worries me.” “The dog worries everyone.” Molly unfolded a crayon-drawn map. “We enter through the side gate during cake.” “Cake creates chaos.” “Exactly. You distract them.” “With what?” “Your juggling.” “I don’t juggle.” “You told me you did.” “I said I struggle.” Molly sighed. “Fine. You announce a magician has arrived.” “Do I know magic?” “You can make confidence disappear.” Bill nodded solemnly. “That’s my signature trick.” A cheer erupted as the birthday boy attacked a piñata shaped like a tax accountant. Molly pointed. “When candy drops, we move. Presents into the wagon.” “The red wagon?” “Yes.” “Small problem.” “What?” Bill revealed a tiny plastic wheel in his palm. “I stepped on it.” Molly stared. “Bill.” “It squeaked at me.” Across the lawn, the tiara dog barked. Molly grabbed the broken wheel. “New plan.” “Run?” “Volunteer to fix the wagon.” Bill brightened. “Then steal presents?” Molly watched a toddler hug a package. “No. Then steal cake.”
created_at
"2026-04-24T21:34:22.872Z"
4/24/2026, 9:34:22 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1524
moderation_latency
(null)
generation_time
9405
tokens_prompt
77
tokens_completion
444
native_tokens_prompt
66
native_tokens_completion
330
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.01023
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0404560aa8ed21290169ebe1def7288193b684afee4cda8073"
is_byok
false
latency
287
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777066462-a7hgzIlDOnc1L7m7uV6H"
session_id
(null)
api_type
"completions"
id
"gen-1777066462-8UXKT0xtMHzOfJa69tiC"
upstream_id
"resp_0404560aa8ed21290169ebe1def7288193b684afee4cda8073"
total_cost
0.01023
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
220
99.83%
Dialogue to Total Word Ratio
Ratio: 52.04%, Deviation: 2.04%
neededClean
false
wordsTotal
221
wordsDialogue
115
60.0089%